Skip to content
Fundamentals

Token

The basic unit of text that AI models process — roughly 3/4 of a word in English. 'Unbelievable' is 3 tokens. Token limits determine how much text a model can process at once.

Why it matters

Tokens are how AI usage is measured and priced, and how limits are enforced. This matters practically: pasting a huge document can exceed a model's capacity or run up costs, and "the AI forgot the start of our chat" usually means you hit a token limit. Knowing tokens exist helps you understand billing on API tools and why very long inputs sometimes get truncated.

A concrete example

The word "unbelievable" might split into pieces like "un," "believ," and "able," so it counts as several tokens, not one. A rough rule of thumb: 1,000 tokens is about 750 English words. So if a tool allows an 8,000-token input, you can fit roughly 6,000 words, a longish article, but not an entire book, before you'd need to trim or split it.

How to use it

As a rough planning figure, a thousand tokens is around 750 English words. That lets you sanity-check before you paste: a long report may not fit, and a loop that processes a thousand documents costs a thousand times one document. If you are paying per token, the cheapest optimisation is usually not a better model but sending less — trimming boilerplate, dropping the parts of a document that do not bear on the question.

The common mistake

Assuming token counts are the same across models and languages. Different tokenizers split text differently, and languages that are not English often need noticeably more tokens for the same content, which changes both cost and how much fits.

Related terms

Put Token into practice

Access 750+ AI models and 60+ tools through Vincony — start free with 100 credits.